Conceptual Vectors and Fuzzy Templates for Discriminating Hyperonymy (is-a) and Meronymy (part-of) relations
نویسنده
چکیده
Hierarchy building from dictionaries and free texts is often viewed as an application of NLP for domain modeling. The reversal (i.e. building and using such hierarchy for Word Sense Disambiguation) is also definitively useful in NLP. Indeed, we do observe that, even in very specialized texts, polysemous terms as well as blurring linguistic phenomena like metonymy or metaphor are frequent. Conceptual vectors are part of a model for meaning representation applicable to lexical disambiguation [Lafourcade, 2001]. We devise some strategies combining vectors and relation templates to automatically construct lexical network able to discriminate between various is-a and part-of relations.
منابع مشابه
Extracting Lexical Relations from Biomedical Text: Learning Parts and Wholes MPhil / PhD Upgrade Report
Lexical relations organise and structure vocabulary. They reflect relations in the real world. Meronymy is the lexical relation between a word representing a part, and a word representing a whole, such as (finger partOf hand). Meronymy is of special importance in biomedicine: structure and process are organised along partitive axes. Anatomy, for example, is rich in part-whole relations. This im...
متن کاملExtracting Lexico-conceptual Knowledge for Developing Persian WordNet
Semantic lexicons and lexical ontologies are some major resources in natural language processing. Developing such resources are time consuming tasks for which some automatic methods are proposed. This paper describes some methods used in semi-automatic development of FarsNet; a lexical ontology for the Persian language. FarsNet includes the Persian WordNet with more than 10000 synsets of nouns,...
متن کاملKnowledge-free Learning of lexical hierarchical paradigmatic relations
This paper represents an attempt at translating statistical methods and properties of rankings in a vector space model into an algorithm that extracts hierarchical paradigmatic relations such as hyperonymy and meronymy. The algorithm is based on simulating semantic similarity through co-occurrence statistics as well as observing symmetry in similarity rankings. A preliminary evaluation based on...
متن کاملGuessing Hierarchies and Symbols for Word Meanings through Hyperonyms and Conceptual Vectors
The NLP team of LIRMM currently works on lexical disambiguation and thematic text analysis [Lafourcade, 2001]. We built a system, with automated learning capabilities, based on conceptual vectors for meaning representation. Vectors are supposed to encode ideas associated to words or expressions. In the framework of knowledge and lexical meaning representation, we devise some conceptual vectors ...
متن کاملMixing Semantic Networks and Conceptual Vectors: The Case of Hyperonymy
In this paper, we focus on lexical semantics, a key issue in Natural Language Processing (NLP) that tends to converge with conceptual Knowledge Representation (KR) and ontologies. When ontological representation is needed, hyperonymy, the closest approximation to the is-a relation, is at stake. In this paper we describe the principles of our vector model (CVM: Conceptual Vector Model), and show...
متن کامل